---
title: "Create Eval"
method: POST
path: "/v1/evals"
tags: ["OpenAI Evals API"]
---

# Create Eval

`POST /v1/evals`

Create a new evaluation.

Model-based routing (for multi-account support):
- Pass model via header: `x-litellm-model: gpt-4-account-1`
- Pass model via query: `?model=gpt-4-account-1`
- Pass model via body: `{"model": "gpt-4-account-1"}`

Example usage:
```bash
curl -X POST "http://localhost:4000/v1/evals"       -H "Authorization: Bearer your-key"       -H "Content-Type: application/json"       -d '{
    "name": "Test Eval",
    "data_source_config": {"type": "file", "file_id": "file-abc123"},
    "testing_criteria": {"graders": [{"type": "llm_as_judge"}]}
  }'
```

Returns: Eval object with id, status, timestamps, etc.

## Query parameters

- `custom_llm_provider` string, nullable

## Response `200`

Successful Response

- Eval — Represents an evaluation from the OpenAI Evals API
  - `id` string, required
  - `object` string
  - `created_at` integer, required
  - `updated_at` integer, nullable
  - `name` string, nullable
  - `data_source_config` object, required
  - `testing_criteria` object[], required
  - `metadata` object, nullable

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/sea-lion/apis/litellm-api.md) · [All operations](https://skmtc.net/sea-lion/apis/litellm-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/sea-lion/litellm-api/revisions/1e929292ddd5/schema)